Triple
T19423019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchess of Franco |
E485905
|
entity |
| Predicate | granteeRelationToFranco |
P135821
|
FINISHED |
| Object | only child of Francisco Franco |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: only child of Francisco Franco | Statement: [Duchess of Franco, granteeRelationToFranco, only child of Francisco Franco]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: granteeRelationToFranco Context triple: [Duchess of Franco, granteeRelationToFranco, only child of Francisco Franco]
-
A.
principalFrenchRepresentative
Indicates that one entity serves as the primary official representative of France in relation to another entity.
-
B.
obligationsOfFrance
Indicates that the specified obligations are those that France is responsible for or bound to fulfill.
-
C.
reservedToFrance
Indicates that something is exclusively allocated or designated for France.
-
D.
laterFrenchCoSovereignLine
Indicates that one entity served as a later co-sovereign (joint ruler) in a French line of succession or rulership relative to another entity.
-
E.
partyRoleOfFrance
Indicates the specific role or capacity that France holds as a party within a given agreement, event, or relationship.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e632169d9c81909a88704c6beb8fe0 |
completed | April 20, 2026, 2:03 p.m. |
| PD | Predicate disambiguation | batch_69e4fd68b1f881908d273de1fee81a75 |
completed | April 19, 2026, 4:06 p.m. |
| PDg | Predicate description generation | batch_69e5004c23308190a087b7941a90725f |
completed | April 19, 2026, 4:18 p.m. |
Created at: April 10, 2026, 1:37 p.m.